Also they only go 94% of their random sample to take the test.
-
-
-
Replying to @joelwatsonfish @SimonDeDeo
I find it incredibly troubling that they acknowledge that accumulated knowledge increases the score, and then think the only the thing they need to control for is age. And they have a non-random sample. And they don’t specify the correlation between AFQT and IQ
2 replies 0 retweets 0 likes -
Replying to @cmkourtu @SimonDeDeo
I'm sure it's in the literature. People like
@StuartJRitchie and@rjhaier would probably know.1 reply 0 retweets 0 likes -
Also probably people like
@pnin1957@Scientific_Bird and@KirkegaardEmil1 reply 0 retweets 0 likes -
Replying to @joelwatsonfish @cmkourtu and
See appendix 3 in The Bell Curve regarding correlation between AFQT score and IQ test batteries.pic.twitter.com/aH2KmLs8xB
2 replies 1 retweet 2 likes -
Replying to @Scientific_Bird @joelwatsonfish and
Those are extremely unimpressive, and none of those test are the WAIS, which is the mostly widely used IQ test to date. With r values that low, it’s completely possible that the r between those test and income is near 0.
1 reply 0 retweets 0 likes -
-
Replying to @joelwatsonfish @Scientific_Bird and
I don’t know, it’s an interesting question, but considering income is fat-tailed, and not even logincome is normal, the idea of correlation really doesn’t apply here.
1 reply 0 retweets 0 likes -
Replying to @cmkourtu @Scientific_Bird and
Well, yeah... I mean, if income is log-normal, and IQ is normal, then the right thing to do is look at correlation between log(income) and IQ. This has been done. It yields a better relationship.
2 replies 1 retweet 0 likes
The difference between these is mostly trivial, waste of time to obsess about.
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.